distilbert-base-uncased_emotion_ft_0416

Bert Model for Emotion Classification

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 4

Framework versions

• Transformers 4.57.5
• Pytorch 2.9.1+cu128
• Datasets 4.5.0
• Tokenizers 0.22.2